© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 11-RES-JB
    11. 14460
    Prev
    Next
    INDEX
    Explanations

    mentions of viruses and related medical terms

    oai_token-act-pair · gpt-3.5-turbo

    references to viruses and viral infections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    fman
    -0.87
    ixel
    -0.86
    anooga
    -0.85
    bell
    -0.77
    notations
    -0.74
    ilts
    -0.74
    insula
    -0.73
    dash
    -0.72
    shire
    -0.71
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.71
    POSITIVE LOGITS
     infection
    1.35
     infections
    1.24
     infect
    1.21
    irus
    1.13
    infect
    1.13
     outbreak
    1.11
     Infect
    1.04
     outbreaks
    1.01
     strains
    1.00
     inoc
    0.99
    Activations Density 0.037%

    No Known Activations